<?php

/**
 * 字符串处理
 *
 * example：
 * <pre>
 *
 * </pre>
 *
 * @name Util_StringHelper
 * @version 
 * @package Util.StringHelper
 */

class Util_StringHelper
{

    /**
     * 按字来切分字符 (UTF－8截字)
     *
     * @param $str String
     * @param $length Integer
     * @param $start Integer
     * @param $encoding String
     * @return String
     */
    public function mbSubstr ($str, $length, $start = 0, $suffix = '...', $encoding = "utf-8")
    {
        $str = trim($str);
        if (mb_strlen($str) == $length)
        {return $str;}
        $strs = mb_substr($str, $start, $length, $encoding);
        if ((mb_strlen($str) / 3) > $length)
        {
            $strs .= $suffix;
        }
        return $strs;
    }

    /**
     * 按字节来切分字符
     *
     * @param $str String
     * @param $length Integer
     * @param $start Integer
     * @param $encoding String
     */
    public function mbStrcut ($str, $length, $start = 0, $encoding = "utf-8")
    {
        return mb_strcut($str, $start, $length, $encoding);
    }

    /**
     * 判定是否是某个编码的合法字串
     *
     * @param $str String
     * @param $coding String
     * @return String
     */
    public function isValidCoding ($str, $coding = "UTF-8")
    {
        return mb_check_encoding($str, $coding);
    }

    /**
     * gbk 转 unicode
     *
     * @param $text String
     * @return String
     */
    public function baseGbkToUnicode ($str)
    {
        $rtext = "";
        preg_match_all("/[\x81-\xfe]?./", $str, $regs);
        foreach ($regs[0] as $v)
        {
            if (ord($v) > 127)
            {
                $rtext .= "&#" . base_convert(bin2hex(iconv("gb2312", "ucs-2", $v)), 16, 10) . ";";
            }
            else
            {
                $rtext .= $v;
            }
        }
        return $rtext;
    }

    /**
     * 转换16进制到UTF－8
     *
     * @param $text String
     * @return String
     */
    public function unicode16ToUtf ($text)
    {
        preg_match_all("/\%u([a-zA-Z0-9]{0,4}+)/", $text, $regs);
        foreach ($regs[0] as $v)
        {
            $to = "&#" . base_convert(str_replace("%u", "", $v), 16, 10) . ";";
            $text = str_replace($v, $to, $text);
        }
        return $text;
    }

    /**
     * utf 装 gbk
     *
     * @param $str String
     * @return String
     */
    public function utfToGbk ($str)
    {
        $info = mb_convert_encoding($str, "gbk", "utf-8");
        return $info;
    }

    /**
     * UTF8 转换
     *
     * @param $str String
     * @return String
     */
    public function gbkToUtf8 ($str)
    {
        $str = mb_convert_encoding($str, "utf-8", "gbk");
        $convmap = array(0x0080, 0xffff, 0x0000, 0xffff);
        // 0x0026, 0x0026, 0x0000, 0xffff); <-这个是转&号为&amp;
        $str = mb_encode_numericentity($str, $convmap, "utf-8");
        return $str;
    }

    /**
     * Hex2Str 解码
     *
     * @param $msg String
     * @return String
     */
    public function Hex2Str ($msg, $isString = true)
    {
        $outstr = "";
        $l = strlen($msg);
        if ($l % 2 != 0)
        {
            $l --;
        }
        $par = "H" . $l;
        $outstr = pack($par, $msg);
        if ($isString == false)
        {return $outstr;}
        return $this->gbkToUtf8($this->unicodeToGBK($outstr));
    }

    /**
     * Str2Hex 编码
     *
     * @param $msg String
     * @return String
     */
    public function Str2Hex ($msg)
    {
        $str = unpack("C*", $this->utf8TOunicode($msg));
        $result = "";
        for ($i = 1; $i <= count($str); $i ++)
        {
            $tmp = DecHex($str[$i]);
            if (strlen($tmp) == 1)
            {
                $tmp = "0" . $tmp;
            }
            $result .= $tmp;
        }
        return $result;
    }

    /**
     * 转换编码
     *
     * @param $str String
     * @return String
     */
    public function gbkToUnicode ($str)
    {
        return mb_convert_encoding($str, "unicode", "gbk");
    }

    /**
     * 转换成GBK
     *
     * @param $str String
     * @return String
     */
    public function unicodeToGBK ($str)
    {
        return mb_convert_encoding($str, "gbk", "unicode");
    }

    /**
     * unicode 转UTF-8
     *
     * @param $str String
     * @return String
     */
    public function unicodeTOUtf8 ($str)
    {
        return mb_convert_encoding($str, "utf-8", "unicode");
    }

    /**
     * UTF-8转unicode
     *
     * @param $str String
     * @return String
     */
    public function utf8TOunicode ($str)
    {
        return mb_convert_encoding($str, "unicode", "utf-8");
    }

    /**
     * 对addslashes处理中文字符出现错误的解决
     *
     * @param $string string 要转义的字符串
     * @param $escape: boolean 是否对中文特殊处理，默认为false
     * @return string
     */
    public function addslash ($string, $escape = false)
    {
        if (! $escape)
        {return addslashes($string);}
        $string = ereg_replace("([^\xA1-\xFE])[\x5c]", "\\1\\", $string);
        $string = str_replace("\\", "\\\\", $string);
        $string = str_replace("'", "\\'", $string);
        $string = str_replace("\"", "\\\"", $string);
        return $string;
    }

    /**
     * CRC转换为16进制
     *
     * @param $str String
     * @return String
     */
    public function crc2Dechex ($val)
    {
        return dechex(crc32($val));
    }

    /**
     * 对象进行编码crc32有符号
     *
     * @param $val String
     * @return String
     */
    public function obj2Crc2 ($val)
    {
        $crc = crc32($val);
        return $crc;
    }

    /**
     * 格式化html代码的 (包括中文)
     *
     * @param $str String
     * @return String
     */
    public function htmlEntities ($str)
    {
        return htmlentities($str);
    }

    /**
     * 格式化html代码的 (不包括中文)
     *
     * @param $str String
     * @return String
     */
    public function htmlSpecialChars ($str)
    {
        return htmlspecialchars($str);
    }

    /**
     *
     *
     *
     * 按字来切分字符 (UTF－8截字) 并 格式化代码
     *
     * @param $str String
     * @param $length Integer
     * @param $start Integer
     * @param $suffix String
     * @param $encoding String
     * @return String
     */
    public function mbSubstrHtml ($str, $length, $start = 0, $suffix = '...', $encoding = "utf-8")
    {
        return $this->htmlSpecialChars($this->mbSubstr($str, $length, $start, $suffix, $encoding));
    }

    /**
     * 替换数据
     *
     * @param $str String
     * @param $pattern String
     * @param $replacement String
     * @return String
     */
    public function pregReplace ($str, $pattern = '/\[(.*?)\]/i', $replacement = '')
    {
        return preg_replace($pattern, $replacement, $str);
    }

    /**
     * 获取字符串首字母, 可传入汉字，字母 ，数字
     *
     * @param $string String
     * @return String
     */
    public function getFirstLetter ($string)
    {
        $string = iconv('utf-8', 'gbk', $string); // 字符编码转换
        $dict = array('a' => 0xB0C4, 'b' => 0xB2C0, 'c' => 0xB4ED, 'd' => 0xB6E9, 'e' => 0xB7A1, 'f' => 0xB8C0, 'g' => 0xB9FD, 'h' => 0xBBF6, 'j' => 0xBFA5, 'k' => 0xC0AB, 'l' => 0xC2E7, 'm' => 0xC4C2, 'n' => 0xC5B5, 'o' => 0xC5BD, 'p' => 0xC6D9, 'q' => 0xC8BA, 'r' => 0xC8F5, 's' => 0xCBF9, 't' => 0xCDD9, 'w' => 0xCEF3, 'x' => 0xD188, 'y' => 0xD4D0, 'z' => 0xD7F9);
        $letter = substr($string, 0, 4);
        if ($letter >= chr(0x81) && $letter <= chr(0xfe))
        {
            $num = hexdec(bin2hex(substr($string, 0, 2)));
            foreach ($dict as $k => $v)
            {
                if ($v >= $num)
                    break;
            }
            return strtoupper($k);
        }
        elseif ((ord($letter) > 64 && ord($letter) < 91) || (ord($letter) > 96 && ord($letter) < 123))
        {
            return strtoupper($letter{0});
        }
        elseif ($letter >= '0' && $letter <= '9')
        {
            return $letter;
        }
        else
        {
            return false;
        }
    }

    /**
     * 去除html标签
     *
     * @param $string String
     * @return String
     */
    public function pregReplaceHtml ($string)
    {
        if (empty($string))
        {return $string;}
        $pattern = array("'<script[^>]*?>[\s\S]*?</script>'si", "'<[\/\!]*?[^<>]*?>'si", "'<iframe[^>]*?>[\s\S]*?</iframe>'si");
        $replacement = '';
        return preg_replace($pattern, $replacement, $string);
    }

    /**
     * 去除危险标签
     *
     * @param $string String
     * @return String
     */
    public function replaceDangerCode ($string)
    {
        if (empty($string))
        {return $string;}
        $pattern = array("'<style[^>]*?>[\s\S]*?</style>'si", "'<iframe[^>]*?>[\s\S]*?</iframe>'si", "'<script[^>]*?>[\s\S]*?</script>'si", "'<link[^>]*?/>'si");
        $replacement = '';
        return preg_replace($pattern, $replacement, $string);
    }

    /**
     * SEO
     *
     * @param $string String
     * @return String
     */
    public function toSEO ($string)
    {
        $search = array(' ', '%20', '&', '?', '@', '\/');
        $replace = array('_', '_', '_', '_', '_', '_');
        $string = str_replace($search, $replace, $string);
        return $string;
    }

    /**
     * 字符替换
     *
     * @param $document String
     * @return String
     */
    public static function striptext ($document)
    {
        $search = array("'<script[^>]*?>.*?</script>'si",         // strip out
                                                          // javascript
        "'<[\/\!]*?[^<>]*?>'si",         // strip out html tags
        "'([\r\n])[\s]+'",         // strip out white space
        "'&(quot|#34|#034|#x22);'i",         // replace html entities
        "'&(amp|#38|#038|#x26);'i",         // added hexadecimal values
        "'&(lt|#60|#060|#x3c);'i", "'&(gt|#62|#062|#x3e);'i", "'&(nbsp|#160|#xa0);'i", "'&(iexcl|#161);'i", "'&(cent|#162);'i", "'&(pound|#163);'i", "'&(copy|#169);'i", "'&(reg|#174);'i", "'&(deg|#176);'i", "'&(#39|#039|#x27);'", "'&(euro|#8364);'i",         // europe
        "'&a(uml|UML);'",         // german
        "'&o(uml|UML);'", "'&u(uml|UML);'", "'&A(uml|UML);'", "'&O(uml|UML);'", "'&U(uml|UML);'", "'&szlig;'i");
        $replace = array("", "", "\\1", "\"", "&", "<", ">", " ", chr(161), chr(162), chr(163), chr(169), chr(174), chr(176), chr(39), chr(128), "?", "?", "?", "?", "?", "?", "?");
        
        return preg_replace($search, $replace, $document);
    }

    public function stripTags ($html)
    {
        $search = array('&nbsp;', "'<script[^>]*?>.*?</script>'si", "'<[\/\!]*?[^<>]*?>'si", "'([\r\n])[\s]+'", "'&(quot|#34|#034|#x22);'i", "'&(amp|#38|#038|#x26);'i", "'&(lt|#60|#060|#x3c);'i", "'&(gt|#62|#062|#x3e);'i", "'&(nbsp|#160|#xa0);'i", "'&(iexcl|#161);'i", "'&(cent|#162);'i", "'&(pound|#163);'i", "'&(copy|#169);'i", "'&(reg|#174);'i", "'&(deg|#176);'i", "'&(#39|#039|#x27);'", "'&(euro|#8364);'i", "'&a(uml|UML);'", "'&o(uml|UML);'", "'&u(uml|UML);'", "'&A(uml|UML);'", "'&O(uml|UML);'", "'&U(uml|UML);'", "'&szlig;'i", "\n", "\r", "\t", "\0", "　");
        return trim(str_replace($search, '', strip_tags($html)));
    }

    /**
     *
     *
     *
     * 得到一个博客的唯一编码
     *
     * @param $uid integer 用户编码
     * @return string
     */
    public function getBlogUuid ($uid = '')
    {
        return uniqid();
    }

    /**
     *
     *
     *
     * 得到一个短链接的唯一编码
     *
     * @param $uid integer 用户编码
     * @return string
     */
    public function getSUrlUuid ($uid = '')
    {
        $sUrl = uniqid('', true);
        return str_replace('.', '', $sUrl);
    }

    /**
     * 转换长链接到短链接
     *
     * @param $url string
     * @return string
     */
    public static function getShortLink ($url)
    {
        $url_int = sprintf('%u', '0x' . hash('crc32', $url) + 0);
        $str = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz1234567890';
        $ret = '';
        while ($url_int > 0)
        {
            $ret .= substr($str, $url_int % 62, 1);
            $url_int = (int) floor($url_int / 62);
        }
        return $ret;
    }

    /**
     * 过滤中文字符串
     *
     * @param $string
     * @param $length
     * @param $charset
     * @param $etc
     * @return unknown_type
     */
    public static function substr_filter ($string, $length = 280, $charset = 'UTF-8', $etc = '...')
    {
        $filter_string = strip_tags(htmlspecialchars_decode($string));
        if (mb_strwidth($filter_string, 'UTF-8') <= $length)
        {return $filter_string;}
        return mb_strimwidth($filter_string, 0, $length, '', $charset) . $etc;
    }

    /**
     * 切割中文字符串
     *
     * @param $string
     * @param $length
     * @param $charset
     * @param $etc
     * @return unknown_type
     */
    public static function substr_cn ($string, $length = 280, $charset = 'UTF-8', $etc = '...')
    {
        if (mb_strwidth($string, 'UTF-8') <= $length)
            return $string;
        return mb_strimwidth($string, 0, $length, '', $charset) . $etc;
    }

    /**
     * 转换中文首字母的函数
     *
     * @param $_String string
     * @param $isInitial boolean 是否只返回首字母
     * @param $_Code string 编码格式 utf8 or gb2312
     * @return string
     */
    public static function Pinyin ($_String, $isInitial = true, $_Code = "utf8")
    {
        $_DataKey = "a|ai|an|ang|ao|ba|bai|ban|bang|bao|bei|ben|beng|bi|bian|biao|bie|bin|bing|bo|bu|ca|cai|can|cang|cao|ce|ceng|cha" . "|chai|chan|chang|chao|che|chen|cheng|chi|chong|chou|chu|chuai|chuan|chuang|chui|chun|chuo|ci|cong|cou|cu|" . "cuan|cui|cun|cuo|da|dai|dan|dang|dao|de|deng|di|dian|diao|die|ding|diu|dong|dou|du|duan|dui|dun|duo|e|en|er" . "|fa|fan|fang|fei|fen|feng|fo|fou|fu|ga|gai|gan|gang|gao|ge|gei|gen|geng|gong|gou|gu|gua|guai|guan|guang|gui" . "|gun|guo|ha|hai|han|hang|hao|he|hei|hen|heng|hong|hou|hu|hua|huai|huan|huang|hui|hun|huo|ji|jia|jian|jiang" . "|jiao|jie|jin|jing|jiong|jiu|ju|juan|jue|jun|ka|kai|kan|kang|kao|ke|ken|keng|kong|kou|ku|kua|kuai|kuan|kuang" . "|kui|kun|kuo|la|lai|lan|lang|lao|le|lei|leng|li|lia|lian|liang|liao|lie|lin|ling|liu|long|lou|lu|lv|luan|lue" . "|lun|luo|ma|mai|man|mang|mao|me|mei|men|meng|mi|mian|miao|mie|min|ming|miu|mo|mou|mu|na|nai|nan|nang|nao|ne" . "|nei|nen|neng|ni|nian|niang|niao|nie|nin|ning|niu|nong|nu|nv|nuan|nue|nuo|o|ou|pa|pai|pan|pang|pao|pei|pen" . "|peng|pi|pian|piao|pie|pin|ping|po|pu|qi|qia|qian|qiang|qiao|qie|qin|qing|qiong|qiu|qu|quan|que|qun|ran|rang" . "|rao|re|ren|reng|ri|rong|rou|ru|ruan|rui|run|ruo|sa|sai|san|sang|sao|se|sen|seng|sha|shai|shan|shang|shao|" . "she|shen|sheng|shi|shou|shu|shua|shuai|shuan|shuang|shui|shun|shuo|si|song|sou|su|suan|sui|sun|suo|ta|tai|" . "tan|tang|tao|te|teng|ti|tian|tiao|tie|ting|tong|tou|tu|tuan|tui|tun|tuo|wa|wai|wan|wang|wei|wen|weng|wo|wu" . "|xi|xia|xian|xiang|xiao|xie|xin|xing|xiong|xiu|xu|xuan|xue|xun|ya|yan|yang|yao|ye|yi|yin|ying|yo|yong|you" . "|yu|yuan|yue|yun|za|zai|zan|zang|zao|ze|zei|zen|zeng|zha|zhai|zhan|zhang|zhao|zhe|zhen|zheng|zhi|zhong|" . "zhou|zhu|zhua|zhuai|zhuan|zhuang|zhui|zhun|zhuo|zi|zong|zou|zu|zuan|zui|zun|zuo";
        $_DataValue = "-20319|-20317|-20304|-20295|-20292|-20283|-20265|-20257|-20242|-20230|-20051|-20036|-20032|-20026|-20002|-19990" . "|-19986|-19982|-19976|-19805|-19784|-19775|-19774|-19763|-19756|-19751|-19746|-19741|-19739|-19728|-19725" . "|-19715|-19540|-19531|-19525|-19515|-19500|-19484|-19479|-19467|-19289|-19288|-19281|-19275|-19270|-19263" . "|-19261|-19249|-19243|-19242|-19238|-19235|-19227|-19224|-19218|-19212|-19038|-19023|-19018|-19006|-19003" . "|-18996|-18977|-18961|-18952|-18783|-18774|-18773|-18763|-18756|-18741|-18735|-18731|-18722|-18710|-18697" . "|-18696|-18526|-18518|-18501|-18490|-18478|-18463|-18448|-18447|-18446|-18239|-18237|-18231|-18220|-18211" . "|-18201|-18184|-18183|-18181|-18012|-17997|-17988|-17970|-17964|-17961|-17950|-17947|-17931|-17928|-17922" . "|-17759|-17752|-17733|-17730|-17721|-17703|-17701|-17697|-17692|-17683|-17676|-17496|-17487|-17482|-17468" . "|-17454|-17433|-17427|-17417|-17202|-17185|-16983|-16970|-16942|-16915|-16733|-16708|-16706|-16689|-16664" . "|-16657|-16647|-16474|-16470|-16465|-16459|-16452|-16448|-16433|-16429|-16427|-16423|-16419|-16412|-16407" . "|-16403|-16401|-16393|-16220|-16216|-16212|-16205|-16202|-16187|-16180|-16171|-16169|-16158|-16155|-15959" . "|-15958|-15944|-15933|-15920|-15915|-15903|-15889|-15878|-15707|-15701|-15681|-15667|-15661|-15659|-15652" . "|-15640|-15631|-15625|-15454|-15448|-15436|-15435|-15419|-15416|-15408|-15394|-15385|-15377|-15375|-15369" . "|-15363|-15362|-15183|-15180|-15165|-15158|-15153|-15150|-15149|-15144|-15143|-15141|-15140|-15139|-15128" . "|-15121|-15119|-15117|-15110|-15109|-14941|-14937|-14933|-14930|-14929|-14928|-14926|-14922|-14921|-14914" . "|-14908|-14902|-14894|-14889|-14882|-14873|-14871|-14857|-14678|-14674|-14670|-14668|-14663|-14654|-14645" . "|-14630|-14594|-14429|-14407|-14399|-14384|-14379|-14368|-14355|-14353|-14345|-14170|-14159|-14151|-14149" . "|-14145|-14140|-14137|-14135|-14125|-14123|-14122|-14112|-14109|-14099|-14097|-14094|-14092|-14090|-14087" . "|-14083|-13917|-13914|-13910|-13907|-13906|-13905|-13896|-13894|-13878|-13870|-13859|-13847|-13831|-13658" . "|-13611|-13601|-13406|-13404|-13400|-13398|-13395|-13391|-13387|-13383|-13367|-13359|-13356|-13343|-13340" . "|-13329|-13326|-13318|-13147|-13138|-13120|-13107|-13096|-13095|-13091|-13076|-13068|-13063|-13060|-12888" . "|-12875|-12871|-12860|-12858|-12852|-12849|-12838|-12831|-12829|-12812|-12802|-12607|-12597|-12594|-12585" . "|-12556|-12359|-12346|-12320|-12300|-12120|-12099|-12089|-12074|-12067|-12058|-12039|-11867|-11861|-11847" . "|-11831|-11798|-11781|-11604|-11589|-11536|-11358|-11340|-11339|-11324|-11303|-11097|-11077|-11067|-11055" . "|-11052|-11045|-11041|-11038|-11024|-11020|-11019|-11018|-11014|-10838|-10832|-10815|-10800|-10790|-10780" . "|-10764|-10587|-10544|-10533|-10519|-10331|-10329|-10328|-10322|-10315|-10309|-10307|-10296|-10281|-10274" . "|-10270|-10262|-10260|-10256|-10254";
        $_TDataKey = explode("|", $_DataKey);
        $_TDataValue = explode("|", $_DataValue);
        
        $_Data = (PHP_VERSION >= "5.0") ? array_combine($_TDataKey, $_TDataValue) : self::_Array_Combine($_TDataKey, $_TDataValue);
        arsort($_Data);
        reset($_Data);
        if ($_Code != "gb2312")
            $_String = self::_U2_Utf8_Gb($_String);
        $_Res = "";
        for ($i = 0; $i < strlen($_String); $i ++)
        {
            $_P = ord(substr($_String, $i, 1));
            if ($_P > 160)
            {
                $_Q = ord(substr($_String, ++ $i, 1));
                $_P = $_P * 256 + $_Q - 65536;
            }
            $_Res .= self::_Pinyin($_P, $_Data, $isInitial);
        }
        return preg_replace("/[^a-z0-9]*/", "", $_Res);
    }

    private static function _U2_Utf8_Gb ($_C)
    {
        $_String = "";
        if ($_C < 0x80)
            $_String .= $_C;
        elseif ($_C < 0x800)
        {
            $_String .= chr(0xC0 | $_C >> 6);
            $_String .= chr(0x80 | $_C & 0x3F);
        }
        elseif ($_C < 0x10000)
        {
            $_String .= chr(0xE0 | $_C >> 12);
            $_String .= chr(0x80 | $_C >> 6 & 0x3F);
            $_String .= chr(0x80 | $_C & 0x3F);
        }
        elseif ($_C < 0x200000)
        {
            $_String .= chr(0xF0 | $_C >> 18);
            $_String .= chr(0x80 | $_C >> 12 & 0x3F);
            $_String .= chr(0x80 | $_C >> 6 & 0x3F);
            $_String .= chr(0x80 | $_C & 0x3F);
        }
        return @iconv("UTF-8", "GBK", $_String);
    }

    private static function _Array_Combine ($_Arr1, $_Arr2)
    {
        for ($i = 0; $i < count($_Arr1); $i ++)
            $_Res[$_Arr1[$i]] = $_Arr2[$i];
        return $_Res;
    }

    private static function _Pinyin ($_Num, $_Data, $isInitial)
    {
        if ($_Num > 0 && $_Num < 160)
            return chr($_Num);
        elseif ($_Num < - 20319 || $_Num > - 10247)
            return "";
        else
        {
            foreach ($_Data as $k => $v)
            {
                if ($v <= $_Num)
                    break;
            }
            if ($isInitial)
                $k = substr($k, 0, 1); // 是否只显示首写
            return $k;
        }
    }

    /**
     * 将URI转为UTF-8编码格式
     *
     * @param $word string
     * @return string
     */
    public static function toUtf8 ($word)
    {
        $word = rawurldecode($word);
        $curchar = mb_detect_encoding($word, 'UTF-8,CP936,EUC-CN,BIG-5,EUC-TW');
        if ($curchar != 'UTF-8')
        {
            $word = mb_convert_encoding($word, 'UTF-8', $curchar);
        }
        if (preg_match('/%u/i', $word))
        {
            $word = self::unescape($word);
        }
        return $word;
    }

    public static function unescape ($str)
    {
        preg_match_all("/%u.{4}|&#x.{4};|&#d+;|.+/U", $str, $r);
        $ar = $r[0];
        foreach ($ar as $k => $v)
            if (substr($v, 0, 2) == "%u" && strlen($v) == 6)
                $ar[$k] = iconv("UCS-2", "UTF-8", pack("H4", substr($v, - 4)));
        return join("", $ar);
    }
    
    /*
     * 用于UTF8编码的程序
    * 获得字符串的长度，一个中文表示3个长度
    * itlearner注释
    */
    public static function utf8_strlen ($str)
    {
        $count = 0;
        for ($i = 0; $i < strlen($str); $i ++)
        {
            $value = ord($str[$i]);
            if ($value > 127)
            {
                $count ++;
                if ($value >= 192 && $value <= 223)
                    $i ++;
                elseif ($value >= 224 && $value <= 239)
                    $i = $i + 2;
                elseif ($value >= 240 && $value <= 247)
                    $i = $i + 3;
                else
                    die('Not a UTF-8 compatible string');
            }
            $count ++;
        }
        return $count;
    }
    
    /**
     * 计算字符的长度
     * 
     * @param string $str 字符串
     * @param int $chinese 指定一个中文算多少个字符
     * @return int
     */
    public static function countStrLen($str,$chinese = 2)
    {
        $count = 0;
        for ($i = 0; $i < strlen($str); $i ++)
        {
            $value = ord($str[$i]);
            if ($value > 127)
            {
                $count += $chinese ;
                if ($value >= 192 && $value <= 223)
                {
                    $i ++;
                }
                elseif ($value >= 224 && $value <= 239)
                {
                    $i = $i + 2;
                }
                elseif ($value >= 240 && $value <= 247)
                {
                    $i = $i + 3;
                }
            }else
            {
                $count ++;
            }
        }
        return $count;
    }
    /**
     * 去掉从word直接粘贴过来的没有用的格式
     * @param unknown_type $content
     * @param unknown_type $allowtags
     * @return mixed
     */
    public static function clearHtml($content,$allowtags='')
    {
         
        mb_regex_encoding('UTF-8');
        //replace MS special characters first
        $search = array('/&lsquo;/u', '/&rsquo;/u', '/&ldquo;/u', '/&rdquo;/u', '/&mdash;/u');
        $replace = array('\'', '\'', '"', '"', '-');
        $content = preg_replace($search, $replace, $content);
        //make sure _all_ html entities are converted to the plain ascii equivalents - it appears
        //in some MS headers, some html entities are encoded and some aren't
        $content = html_entity_decode($content, ENT_QUOTES, 'UTF-8');
        //try to strip out any C style comments first, since these, embedded in html comments, seem to
        //prevent strip_tags from removing html comments (MS Word introduced combination)
        if(mb_stripos($content, '/*') !== FALSE){
            $content = mb_eregi_replace('#/\*.*?\*/#s', '', $content, 'm');
        }
        //introduce a space into any arithmetic expressions that could be caught by strip_tags so that they won't be
        //'<1' becomes '< 1'(note: somewhat application specific)
        $content = preg_replace(array('/<([0-9]+)/'), array('< $1'), $content);
         
        $content = strip_tags($content, $allowtags);
        //eliminate extraneous whitespace from start and end of line, or anywhere there are two or more spaces, convert it to one
        $content = preg_replace(array('/^\s\s+/', '/\s\s+$/', '/\s\s+/u'), array('', '', ' '), $content);
        //strip out inline css and simplify style tags
        $search = array('#<(strong|b)[^>]*>(.*?)</(strong|b)>#isu', '#<(em|i)[^>]*>(.*?)</(em|i)>#isu', '#<u[^>]*>(.*?)</u>#isu');
        $replace = array('<b>$2</b>', '<i>$2</i>', '<u>$1</u>');
        $content = preg_replace($search, $replace, $content);
         
        //on some of the ?newer MS Word exports, where you get conditionals of the form 'if gte mso 9', etc., it appears
        //that whatever is in one of the html comments prevents strip_tags from eradicating the html comment that contains
        //some MS Style Definitions - this last bit gets rid of any leftover comments */
        $num_matches = preg_match_all("/\<!--/u", $content, $matches);
        if($num_matches){
            $content = preg_replace('/\<!--(.)*--\>/isu', '', $content);
        }
        return $content;
    }
}